© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 124500
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting related to coding and program structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بÙĪابة
    -0.09
    atic
    -0.07
    endor
    -0.07
     OnCollision
    -0.06
    елен
    -0.06
    olis
    -0.06
    ÑĥÑĩа
    -0.06
    qui
    -0.06
     grátis
    -0.06
     solitary
    -0.06
    POSITIVE LOGITS
     etc
    0.07
    _ctxt
    0.06
     éĸ
    0.06
    usize
    0.06
    æĪ²
    0.06
    nodoc
    0.06
    inning
    0.06
    osi
    0.06
    ãģĿãģĹãģ¦
    0.06
     ÑĤоÑīо
    0.05
    Activations Density 0.245%

    No Known Activations